Connections Between Pairs of Filters Improve the Accuracy of Convolutional Neural Networks

Researchers have demonstrated that convolutional neural networks can achieve higher accuracy by introducing learnable pairwise connections between filters, moving beyond traditional pointwise activation functions. The new approach allows networks to adapt connection functions across layers, improving performance on specific tasks.

arXiv:2606.13736v1 Announce Type: new Abstract: While researchers continue to find new and improved network structures for CNNs, most of the newly invented architectures still rely on the traditional pattern of stacking convolutional blocks and separating them with pointwise activation functions. However, there are drawbacks to a network purely building on pointwise nonlinearities. One alternative is to introduce a pairwise connection between two filters of a network. Typical connection functions use multiplications or the minimum operation to realize logical AND connections. In this paper, we go one step further by demonstrating that CNNs can benefit from more general connections, which include parameters that are learned. With such parameters, the network is able to implement different connections in different network layers and better adapt the connection function to the task at hand.